Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2954 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.8229. Min Act: -0.1699

Data Index: 6464765 (Open Web Text)

Max Activating Token Index: 430

Text #1

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.8156. Min Act: -0.1700

Data Index: 2769763 (Open Web Text)

Max Activating Token Index: 338

Text #2

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.8017. Min Act: -0.1700

Data Index: 2312039 (Open Web Text)

Max Activating Token Index: 244

Text #3

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7832. Min Act: -0.1690

Data Index: 7976082 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7862. Min Act: -0.1700

Data Index: 5844483 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7848. Min Act: -0.1700

Data Index: 7146192 (Open Web Text)

Max Activating Token Index: 663

Text #6

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7849. Min Act: -0.1699

Data Index: 7171679 (Open Web Text)

Max Activating Token Index: 372

Text #7

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7673. Min Act: -0.1700

Data Index: 503419 (Open Web Text)

Max Activating Token Index: 329

Text #8

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7825. Min Act: -0.1699

Data Index: 6849406 (Open Web Text)

Max Activating Token Index: 52

Text #9

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7600. Min Act: -0.1700

Data Index: 7721500 (Open Web Text)

Max Activating Token Index: 348

Text #10

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7667. Min Act: -0.1700

Data Index: 5750465 (Open Web Text)

Max Activating Token Index: 896

Text #11

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7616. Min Act: -0.1690

Data Index: 6704172 (Open Web Text)

Max Activating Token Index: 479

Text #12

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7623. Min Act: -0.1700

Data Index: 697426 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7582. Min Act: -0.1700

Data Index: 5615382 (Open Web Text)

Max Activating Token Index: 292

Text #14

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7611. Min Act: -0.1700

Data Index: 4484744 (Open Web Text)

Max Activating Token Index: 531

Text #15

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7587. Min Act: -0.1700

Data Index: 2502287 (Open Web Text)

Max Activating Token Index: 94

Text #16

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7612. Min Act: -0.1700

Data Index: 6326796 (Open Web Text)

Max Activating Token Index: 90

Text #17

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7640. Min Act: -0.1700

Data Index: 4293965 (Open Web Text)

Max Activating Token Index: 498

Text #18

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7631. Min Act: -0.1700

Data Index: 7347611 (Open Web Text)

Max Activating Token Index: 206

Text #19

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.7629. Min Act: -0.1700

Data Index: 188850 (Open Web Text)

Max Activating Token Index: 421